larger batch size

config/ppo/Tennis.yaml

 behaviors:
   Tennis:
     trainer: ppo
-    batch_size: 2048
-    buffer_size: 20480
+    batch_size: 4096
+    buffer_size: 40960
-    epsilon: 0.1
+    epsilon: 0.2
     hidden_units: 512
     lambd: 0.95
     learning_rate: 0.0003